Blog
Claude Code from your phone: what actually works in 2026
The question people actually mean is one of two things, and they have completely different answers: run the agent somewhere else, or reach the one already running on your Mac.
There are three distinct answers and picking the wrong one wastes an afternoon. Claude Code on the web runs the session on Anthropic's cloud VMs from a GitHub clone, not your working copy. Remote Control keeps the session on your machine and connects claude.ai or the Claude mobile app to it, so your filesystem and MCP servers stay local. A third-party bridge does the same attaching trick for agents that have no remote story of their own. The deciding question is not which is most convenient, it is what leaves your machine: all three send conversation text to a server, and they differ in how much.
First, which question are you asking
Two different problems get typed as the same search, and the answers do not overlap.
- Run it elsewhere: you want work happening while your laptop is shut. That is a cloud session, and the code it edits is a clone of your repository, not your working copy.
- Reach what is already running: the agent is on your Mac, it stopped to ask something, and you are not at your desk. That is remote control of a local session, and nothing moves.
Claude Code on the web, and the mobile app
Anthropic runs sessions on their own cloud VMs at claude.ai/code, and you can monitor them from the Claude mobile app. The VM clones your repository's GitHub remote at your current branch, so local commits you have not pushed are not there, and a repository with no GitHub remote is uploaded as a bundle instead.
It is the right answer when the work is self-contained and you want it running while you are away. It is the wrong answer when the task depends on your machine: your local uncommitted state, a service running on localhost, a tool you have installed and not committed.
Worth knowing for anyone reading a security policy: sessions run in isolated Anthropic-managed VMs, network access is limited by default, and git credentials stay outside the sandbox with a proxy authenticating on the session's behalf. That is a serious design, and it is theirs rather than something you configure.
Remote Control: the local session, from your phone
This is the one most people are actually looking for, and it is first-party. Running claude remote-control, or /remote-control inside a session, connects claude.ai/code and the Claude iOS and Android apps to a session running on your machine. Claude keeps executing locally the whole time, so your filesystem, your MCP servers and your project configuration stay available, and you can send messages from the terminal, the browser and the phone interchangeably.
It is available on Pro, Max, Team and Enterprise, though not with API-key authentication, and an Owner has to enable it on Team and Enterprise. If you run Claude Code and want to answer it from the couch, start here rather than with anything else on this page.
The trade is stated plainly in Anthropic's own documentation, and it is the thing to read before turning it on: while Remote Control is connected, the session transcript, including your messages, Claude's responses and tool activity, is stored on Anthropic servers. Execution stays on your machine; the record of it does not. Organisations with Zero Data Retention cannot use it at all.
What is left for a third-party bridge
Given that, the honest question is what a non-Anthropic tool adds, and there are two answers.
The first is the other agents. Remote Control is for Claude Code. If your afternoon is a Codex pane, a Gemini CLI pane and an Aider pane, none of them has a remote story, and the one that stopped to ask you a question is as likely to be one of those as it is to be Claude.
The second is how much leaves the machine. A bridge that only needs to render a conversation and route a reply does not need your tool output or your scrollback, and can delete what it held once the session stops being live. That is a smaller surface than a synced transcript that includes tool activity, and it is worth comparing directly rather than assuming any option is the private one.
How this works in Forkbench
Forkbench is a Mac app for running coding agents, and Talk is its remote surface. It attaches to a conversation already open on your Mac from any browser or phone, so you read what the agent asked and reply, and it routes back to that terminal. It is attach-only by design: it cannot start a session, because a remote surface that can start work is a remote surface that can start work you did not ask for.
What it adds over the first-party option is that it does not care which vendor's agent is in the pane, and that a Thread shows you which of its panes is blocked rather than leaving you to check each one. Sleep Control keeps the Mac awake with the lid shut so the session is still there when you look.
What crosses the network, stated as plainly as Anthropic states theirs: to render a conversation in a browser and route your reply to the right terminal, the readable text of that live conversation and its title pass through us. Raw tool output and terminal scrollback are never sent at all, and a conversation that is not on a shared board is deleted a few minutes after it stops being live. Your notes and Vault secrets are sealed under keys we do not hold and never work this way. Talk is part of Pro.
Related: Answer a blocked agent from your phone
Frequently asked
Can I run Claude Code on my phone?
Not the agent itself. Two things are possible and they are different. Claude Code on the web runs a session on Anthropic's cloud VMs and you monitor it from the Claude mobile app, working from a GitHub clone rather than your local checkout. Remote Control keeps the session on your Mac and connects the phone to it, so execution and filesystem access stay local. If the task depends on your machine's state, you want the second.
What is the difference between Claude Code on the web and Remote Control?
Where the code runs. Web sessions execute on Anthropic-managed cloud VMs that clone your repository's GitHub remote, so unpushed local commits are not there. Remote Control leaves the session running on your machine and connects a browser or the mobile app to it, keeping your filesystem, MCP servers and project configuration available. Web is for work that should continue while your laptop is shut; Remote Control is for reaching work that is already running.
Does Remote Control send my code to Anthropic?
Execution and filesystem access stay on your machine, but the record does not. Anthropic's documentation states that while Remote Control is connected, the session transcript including your messages, Claude's responses and tool activity is stored on Anthropic servers, retained under their data usage policy. Organisations with Zero Data Retention cannot enable it. That is a reasonable design for what it does; it is worth knowing before you turn it on rather than after.
How do I answer a Codex or Gemini CLI agent from my phone?
Remote Control is Claude Code only, so for other vendors you need something that attaches to the terminal rather than to the agent. Forkbench's Talk does that for whatever is running in a pane, which matters when the agent that stopped to ask you something is not the Claude one. Expect any such bridge to send the conversation text to a server to render it; ask what else it sends, because tool output and scrollback are the parts worth keeping local.
Can I start a new agent session from my phone?
With a cloud session, yes, that is what it is for. With anything attaching to a local session, be careful what you wish for: a remote surface that can spawn work is a remote surface that can spawn work you did not intend, on a machine you are not sitting at. Forkbench deliberately does not allow it, and the useful remote actions are unblocking, redirecting and queueing an instruction into something already running.